Skip to content
Documentation
Contact
← Back to documentation
Technical Reference

Mistral AI

Mistral AI provides state-of-the-art open-weight and hosted language models for text generation, embeddings, and reasoning tasks.

CategoryArtificial Intelligence
Authenticationcustom
Version0.3.0
Published scopes0 published scopes
Last updatedSeptember 21, 2026

Overview

Connect Mistral AI with Flows360

Mistral AI provides state-of-the-art open-weight and hosted language models for text generation, embeddings, and reasoning tasks.

Use the Mistral AI connector to include its declared actions and events in Flows360 workflows without duplicating the integration logic inside each consuming system. This pinned connector version currently exposes 6 actions and no declared triggers.

Available actions

  • Ask Mistral
  • Create Embeddings
  • Upload File
  • Run OCR
  • List Models
  • Custom API Call

Available triggers

  • No triggers are declared in this pinned package.

The capability list above is generated from the exact reviewed connector package so the public description stays aligned with the version Flows360 operates.

Technical guide

Technical reference

Package identity

  • Connector: Mistral AI
  • Package: @activepieces/piece-mistral-ai@0.3.0
  • Exact artifact digest: sha256:af792cd54b2518c7d0de0f16a2f4ea3dd1fe1f1a157de406af57e10a852d00f3
  • Runtime: Activepieces-compatible deterministic worker
  • Source: the exact reviewed Activepieces source

Authentication

SECRET TEXT, CUSTOM AUTH. Connection values are tenant-specific and remain in the consuming Studio instance; CDK stores definitions and field metadata, not customer credential values.

Action contracts

  • Ask Mistral (create_chat_completion), Ask Mistral anything you want! Classification: read.
  • Create Embeddings (create_embeddings), Creates new embedding in Mistral AI. Classification: read.
  • Upload File (upload_file), Upload a file to Mistral AI (e.g., for fine-tuning or context storage). Classification: read.
  • Run OCR (run_ocr), Extract text from PDFs and images using mistral-ocr-latest. To OCR a file from a previous step, run Upload File first (with purpose=ocr) and pass the returned id here. Classification: read.
  • List Models (list_models), Retrieves a list of available Mistral AI models. Classification: read.
  • Custom API Call (custom_api_call), Make a custom API call to a specific endpoint Classification: read.

Trigger contracts

  • No trigger delivery contracts are declared.

Verification

Deterministic execution evidence is recorded for the pinned artifact, including 1 exercised action entrypoint and 0 exercised trigger entrypoints.

Capability summary

Authenticationcustom
Supported objects6
Supported actions6
TriggersNone published

Authentication

Authentication method: custom

Authentication profiles

connection · custom
  • API Key Required · protected credential
connection_2 · custom
  • Cloudflare Account ID Required
  • Gateway ID Required
  • Gateway Auth Token Optional · protected credential
  • Mistral API Key Optional · protected credential

Supported objects

ObjectReadWriteNotes
Ask Mistral Yes No Ask Mistral anything you want!
Create Embeddings Yes No Creates new embedding in Mistral AI.
Upload File Yes No Upload a file to Mistral AI (e.g., for fine-tuning or context storage).
Run OCR Yes No Extract text from PDFs and images using mistral-ocr-latest. To OCR a file from a previous step, run Upload File first (with purpose=ocr) and pass the returned id here.
List Models Yes No Retrieves a list of available Mistral AI models.
Custom API Call Yes No Make a custom API call to a specific endpoint

Supported actions

Ask Mistral · Read

Ask Mistral anything you want!

create_chat_completion · Risk: low · Retry: safe

Inputs

  • model · string · Required, Select a Mistral model. List is fetched live from your account.
  • prompt · string · Required
  • temperature · number · Optional, Controls randomness: Lowering results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive.
  • top_p · number · Optional, An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
  • max_tokens · number · Optional
  • random_seed · number · Optional
  • timeout · number · Optional
Create Embeddings · Read

Creates new embedding in Mistral AI.

create_embeddings · Risk: low · Retry: safe

Inputs

  • input · array · Required, The input text for which to create an embedding.
  • timeout · number · Optional
Upload File · Read

Upload a file to Mistral AI (e.g., for fine-tuning or context storage).

upload_file · Risk: low · Retry: safe

Inputs

  • file · object · Required, The file to upload (max 512MB).For fine tuning purspose provide .jsonl file.
  • purpose · string · Required, Purpose of the file.
Run OCR · Read

Extract text from PDFs and images using mistral-ocr-latest. To OCR a file from a previous step, run Upload File first (with purpose=ocr) and pass the returned id here.

run_ocr · Risk: low · Retry: safe

Inputs

  • model · string · Required
  • documentSource · string · Required, Where the document or image to OCR comes from.
  • sourceFields · object · Required
  • pages · array · Optional, Optional zero-based page indices to process. Leave empty for all pages.
  • includeImageBase64 · boolean · Optional, Return embedded images encoded as base64 alongside the Markdown.
  • timeout · number · Optional
List Models · Read

Retrieves a list of available Mistral AI models.

list_models · Risk: low · Retry: safe

Custom API Call · Read

Make a custom API call to a specific endpoint

custom_api_call · Risk: low · Retry: safe

Inputs

  • url · object · Required
  • method · string · Required
  • headers · object · Optional, Authorization headers are injected automatically from your connection.
  • queryParams · object · Optional, Appended to the URL as ?key=value.
  • body_type · string · Optional
  • body · object · Optional
  • response_is_binary · boolean · Optional, Enable for files like PDFs, images, etc.
  • failsafe · boolean · Optional, On a failed request, output the error instead of failing the step.
  • timeout · number · Optional, Seconds to wait for a response. Empty: up to the flow limit (10 min).
  • followRedirects · boolean · Optional, Follow 3xx redirects instead of returning them as the response.

Setup

Setup

  1. Add the Mistral AI connector to the workflow in the target Flows360 Studio instance.
  2. Create or select the tenant-specific connection required by the connector. Connection secrets remain in the Studio connection boundary and are not copied into CDK documentation.
  3. Provide the connection fields declared by the pinned package:
  • Cloudflare Account ID (accountId), required.
  • Gateway ID (gatewayId), required.
  • Gateway Auth Token (gatewayAuthToken), optional; stored as a sensitive connection value.
  • Mistral API Key (mistralApiKey), optional; stored as a sensitive connection value.
  1. Select the required action or trigger and complete its declared input fields. Required and optional inputs are defined by the exact package schema.
  2. Test the workflow in the appropriate environment before enabling production scheduling or event delivery.

Limitations

Limitations and operational notes

  • This content describes @activepieces/piece-mistral-ai@0.3.0; provider behaviour can change independently and should be revalidated when the provider or connector version changes.
  • Only the 6 actions and 0 triggers declared by this pinned package are represented here.
  • Tenant credentials and connection values are not stored in the public connector record.
  • Provider-side permissions, account entitlements, quotas and rate limits remain subject to the connected provider account and are not inferred when the package does not declare them.
  • Deterministic execution evidence is recorded for the pinned artifact, including 1 exercised action entrypoint and 0 exercised trigger entrypoints.

Troubleshooting

Why canu2019t the connector authenticate?

Check the tenant connection in Studio and confirm every required Mistral AI connection field is present. Re-authorise OAuth-based connections if the provider token or consent has expired. Do not place credential values in CDK content or logs.

Why is an action or trigger unavailable?

Confirm that the workflow is using @activepieces/piece-mistral-ai@0.3.0 and compare the requested capability with the declared action and trigger list for this version. A capability that is not declared by the pinned package should not be presented as supported.

What should I check after a provider-side change?

Revalidate authentication, required fields, action/trigger behaviour and provider documentation before publishing refreshed connector content or moving a new package version into production.

github.com